Dynamic segmentation and occupancy scoring in edge environments with mobile devices for real-time decision making

Abstract

Occupancy aware decision-making is disclosed. Positions of entities in an environment are determined. Stationary entities are used as markers to segment the environment. Positions of non-stationary entities are used to determine an occupancy score for each of the segments. Decision making operations, such as pathfinding for mobile entities, can be performed using the occupancy scores of the segments. The occupancy scores and segmentation adapt to changes in the environment.

What is claimed is: 
     
         1 . A method comprising:
 reading tags associated with entities in an environment using a positioning system to determine positioning data for each of the entities in the environment, wherein each of the tags is associated with an entity;   identifying markers based on the positioning data, wherein the markers include entities that are currently stationary;   segmenting the environment to generate a segmented space that includes segments, wherein each of the segments is associated with one of the markers;   determining an occupancy score for each of the segments based on the positioning data of mobile entities in the environment for a current cycle; and   performing an occupancy-aware operation based on the occupancy scores.   
     
     
         2 . The method of  claim 1 , wherein the positioning system comprises an RFID system including RFID readers, wherein the tags are RFID tags. 
     
     
         3 . The method of  claim 1 , wherein the positioning data is associated with the current cycle and includes one or more positions for each of the tags. 
     
     
         4 . The method of  claim 1 , wherein the markers are associated with one or more of permanently stationary entities, movable entities, and currently stationary mobile entities for the current cycle. 
     
     
         5 . The method of  claim 1 , wherein mobile entities that overlap with multiple segments contribute to the occupancy scores of the multiple segments. 
     
     
         6 . The method of  claim 5 , wherein a position of each of the entities includes a deviation. 
     
     
         7 . The method of  claim 1 , further comprising dynamically adjusting the occupancy scores. 
     
     
         8 . The method of  claim 7 , wherein dynamically adjusting the occupancy scores includes one or more of:
 starting a new cycle;   determining stationary entities for the new cycle to identify a new set of markers;   segmenting the space based on the new set of markers to generate a new segmented space; and   determining occupancy scores based on mobile active entities in the new segmented space.   
     
     
         9 . The method of  claim 1 , further comprising projecting the occupancy scores into a different representation required for the occupancy-aware operation. 
     
     
         10 . The method of  claim 1 , wherein the occupancy aware operation is a pathfinding operation in the environment. 
     
     
         11 . A non-transitory storage medium having stored therein instructions that are executable by one or more hardware processors to perform operations comprising:
 reading tags associated with entities in an environment using a positioning system to determine positioning data for each of the entities in the environment, wherein each of the tags is associated with an entity;   identifying markers based on the positioning data, wherein the markers include entities that are currently stationary;   segmenting the environment to generate a segmented space that includes segments, wherein each of the segments is associated with one of the markers;   determining an occupancy score for each of the segments based on the positioning data of mobile entities in the environment for a current cycle; and   performing an occupancy-aware operation based on the occupancy scores.   
     
     
         12 . The non-transitory storage medium of  claim 11 , wherein the positioning system comprises an RFID system including RFID readers, wherein the tags are RFID tags. 
     
     
         13 . The non-transitory storage medium of  claim 11 , wherein the positioning data is associated with the current cycle and includes one or more positions for each of the tags. 
     
     
         14 . The non-transitory storage medium of  claim 11 , wherein the markers are associated with one or more of permanently stationary entities, movable entities, and currently stationary mobile entities for the current cycle. 
     
     
         15 . The non-transitory storage medium of  claim 11 , wherein mobile entities that overlap with multiple segments contribute to the occupancy scores of the multiple segments. 
     
     
         16 . The non-transitory storage medium of  claim 15 , wherein a position of each of the entities includes a deviation. 
     
     
         17 . The non-transitory storage medium of  claim 11 , further comprising dynamically adjusting the occupancy scores. 
     
     
         18 . The non-transitory storage medium of  claim 17 , wherein dynamically adjusting the occupancy scores includes one or more of:
 starting a new cycle;   determining stationary entities for the new cycle to identify a new set of markers;   segmenting the space based on the new set of markers to generate a new segmented space; and   determining occupancy scores based on mobile active entities in the new segmented space.   
     
     
         19 . The non-transitory storage medium of  claim 11 , further comprising projecting the occupancy scores into a different representation required for the occupancy-aware operation. 
     
     
         20 . The non-transitory storage medium of  claim 11 , wherein the occupancy aware operation is a pathfinding operation in the environment.